English
Related papers

Related papers: Optimal Subarchitecture Extraction For BERT

200 papers

Recurrent neural network (RNN)'s architecture is a key factor influencing its performance. We propose algorithms to optimize hidden sizes under running time constraint. We convert the discrete optimization into a subset selection problem.…

Machine Learning · Statistics 2018-02-22 Junqi Jin , Ziang Yan , Kun Fu , Nan Jiang , Changshui Zhang

Pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, while the superior performance comes with high demand in computational resources, which hinders the application in low-latency IR systems. We…

Information Retrieval · Computer Science 2020-02-18 Wenhao Lu , Jian Jiao , Ruofei Zhang

Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability.…

Computation and Language · Computer Science 2020-09-29 Jean-Philippe Corbeil , Hadi Abdi Ghadivel

This paper describes a memory-efficient transformer model designed to drive a reduction in memory usage and execution time by substantial orders of magnitude without impairing the model's performance near that of the original model.…

Machine Learning · Computer Science 2025-01-03 Krisvarish V , Priyadarshini T , K P Abhishek Sri Saai , Vaidehi Vijayakumar

BERT-based architectures currently give state-of-the-art performance on many NLP tasks, but little is known about the exact mechanisms that contribute to its success. In the current work, we focus on the interpretation of self-attention,…

Computation and Language · Computer Science 2019-09-12 Olga Kovaleva , Alexey Romanov , Anna Rogers , Anna Rumshisky

Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different…

Computation and Language · Computer Science 2019-08-16 Yaru Hao , Li Dong , Furu Wei , Ke Xu

We introduce the CUDA Tensor Transpose (cuTT) library that implements high-performance tensor transposes for NVIDIA GPUs with Kepler and above architectures. cuTT achieves high performance by (a) utilizing two GPU-optimized transpose…

Mathematical Software · Computer Science 2017-05-05 Antti-Pekka Hynninen , Dmitry I. Lyakh

Due to high accuracy, BERT-like models have been widely adopted by text mining and web searching. However, large BERT-like models suffer from inefficient online inference, facing the following two problems on GPUs: (1) their high accuracy…

Machine Learning · Computer Science 2025-03-19 Weiyan Wang , Yilun Jin , Yiming Zhang , Victor Junqiu Wei , Han Tian , Li Chen , Jinbao Xue , Yangyu Tao , Di Wang , Kai Chen

In recent years, researchers tend to pre-train ever-larger language models to explore the upper limit of deep models. However, large language model pre-training costs intensive computational resources and most of the models are trained from…

Computation and Language · Computer Science 2021-10-15 Cheng Chen , Yichun Yin , Lifeng Shang , Xin Jiang , Yujia Qin , Fengyu Wang , Zhi Wang , Xiao Chen , Zhiyuan Liu , Qun Liu

Transformer-based language models such as BERT have achieved the state-of-the-art performance on various NLP tasks, but are computationally prohibitive. A recent line of works use various heuristics to successively shorten sequence length…

Computation and Language · Computer Science 2022-03-29 Xin Huang , Ashish Khetan , Rene Bidart , Zohar Karnin

Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. However, their substantial memory and computational requirements…

Computation and Language · Computer Science 2026-03-25 Riccardo Bravin , Massimo Pavan , Hazem Hesham Yousef Shalby , Fabrizio Pittorino , Manuel Roveri

As language models have grown in parameters and layers, it has become much harder to train and infer with them on single GPUs. This is severely restricting the availability of large language models such as GPT-3, BERT-Large, and many…

Computation and Language · Computer Science 2022-12-29 Jasdeep Singh Grover , Bhavesh Gawri , Ruskin Raj Manku

Large-scale pre-trained language models have shown remarkable results in diverse NLP applications. Unfortunately, these performance gains have been accompanied by a significant increase in computation time and model size, stressing the need…

Computation and Language · Computer Science 2021-09-27 Cristóbal Eyzaguirre , Felipe del Río , Vladimir Araujo , Álvaro Soto

We present a new semi-external algorithm that builds the Burrows--Wheeler transform variant of Bauer et al. (a.k.a., BCR BWT) in linear expected time. Our method uses compression techniques to reduce computational costs when the input is…

Data Structures and Algorithms · Computer Science 2023-08-15 Diego Díaz-Domínguez , Gonzalo Navarro

Bayesian Additive Regression Trees (BART) is a nonparametric Bayesian regression technique based on an ensemble of decision trees. It is part of the toolbox of many statisticians. The overall statistical quality of the regression is…

Machine Learning · Statistics 2025-07-10 Giacomo Petrillo

Pre-trained language models have shown remarkable results on various NLP tasks. Nevertheless, due to their bulky size and slow inference speed, it is hard to deploy them on edge devices. In this paper, we have a critical insight that…

Computation and Language · Computer Science 2021-09-17 Chenhe Dong , Guangrun Wang , Hang Xu , Jiefeng Peng , Xiaozhe Ren , Xiaodan Liang

Hidden-unit BERT (HuBERT) is a widely-used self-supervised learning (SSL) model in speech processing. However, we argue that its fixed 20ms resolution for hidden representations would not be optimal for various speech-processing tasks since…

Sound · Computer Science 2023-06-26 Jiatong Shi , Yun Tang , Hirofumi Inaguma , Hongyu GOng , Juan Pino , Shinji Watanabe

Recent progress in the Natural Language Processing domain has given us several State-of-the-Art (SOTA) pretrained models which can be finetuned for specific tasks. These large models with billions of parameters trained on numerous GPUs/TPUs…

Machine Learning · Computer Science 2021-09-24 Kamal Raj Kanakarajan , Bhuvana Kundumani , Malaikannan Sankarasubbu

Fine-tuning and inference with large Language Models (LM) are generally known to be expensive. Parameter-efficient fine-tuning over pretrained LMs reduces training memory by updating a small number of LM parameters but does not improve…

Computation and Language · Computer Science 2024-06-05 Bowen Zhao , Hannaneh Hajishirzi , Qingqing Cao

Although BERT based relation classification (RC) models have achieved significant improvements over the traditional deep learning models, it seems that no consensus can be reached on what is the optimal architecture. Firstly, there are…

Computation and Language · Computer Science 2020-09-29 Wei Zhu , Xipeng Qiu , Yuan Ni , Guotong Xie
‹ Prev 1 3 4 5 6 7 10 Next ›